# Trust

Trust checks websites and GitHub repositories for security issues, exposed secrets, and unsafe dependencies. Use it to inspect a project and get a structured repair plan.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · 491 installs
- Author: trust-security
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://smithery.ai/server/trust-security/scanner
- Updated: 2026-03-09
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/trust

## What it does

Trust sends HTTP requests to a live website to look for security flaws. Its repository scan examines GitHub project files for vulnerabilities, exposed credentials, and risky dependencies. Separate tools inspect code for security patterns and check for leaked secrets. A website scan needs a reachable URL; a repository scan uses a GitHub repository URL.

You can retrieve results after starting a scan, then ask for a repair plan with file paths, line numbers, and code before and after each change. That gives you concrete details to work from. Trust connects over HTTP and supports Claude Code, Codex, Cursor, and the other listed platforms.

## Requirements
- Remote server: `https://scanner--trust-security.run.tools`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http scanner https://scanner--trust-security.run.tools
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add trust --url https://scanner--trust-security.run.tools
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "trust": {
            "url": "https://scanner--trust-security.run.tools"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "trust": {
            "type": "http",
            "url": "https://scanner--trust-security.run.tools"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http trust https://scanner--trust-security.run.tools
```

## When to use it
- Check a live website for security flaws
- Find exposed credentials in a GitHub repository
- Spot unsafe dependencies
- Get repair steps linked to files and line numbers

## Example prompts
- Scan `https://example.com` for security issues.
- Check this GitHub repository for exposed secrets and risky dependencies.
- Review this code for security problems and give me a repair plan.

## Similar
- [ghost-scan-code](https://affpapa.org/en/nevibecode/skills/ghost-scan-code.md) — skill · 5700 installs
- [agentic-security-scanner](https://affpapa.org/en/nevibecode/skills/agentic-security-scanner.md) — skill · 467 installs
- [vulnerability-scanning](https://affpapa.org/en/nevibecode/skills/vulnerability-scanning.md) — skill · 621 installs
- [vulnhunter-security-scanner](https://affpapa.org/en/nevibecode/skills/vulnhunter-security-scanner.md) — skill · 101 installs
- [zero-trust](https://affpapa.org/en/nevibecode/skills/zero-trust.md) — skill · 389 installs
- [agent-bom](https://affpapa.org/en/nevibecode/mcp/agent-bom.md) — MCP server · ★ 38 repo stars

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
